© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18260
    Prev
    Next
    INDEX
    Explanations

    Python tokenizer loading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     algebraic
    0.29
    sdk
    0.28
    rosine
    0.28
    ucus
    0.28
    ㄼ
    0.27
    yaf
    0.27
    iyet
    0.27
    äum
    0.26
    immon
    0.26
    Conclusions
    0.26
    POSITIVE LOGITS
     RUN
    0.31
     ентитету
    0.31
    閘
    0.31
    createSprite
    0.30
    Run
    0.30
     tete
    0.30
     gate
    0.30
     월
    0.29
     тестирование
    0.29
     kare
    0.29
    Activations Density 0.002%

    No Known Activations